ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Anomaly-based Alzheimer's disease detection using entropy-based probability Positron Emission Tomography images

  • Received : 2023.03.27
  • Accepted : 2024.01.08
  • Published : 2024.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

Keywords

Acknowledgement

This research was supported by BB21plus funded by Busan Metropolitan City and Busan Institute for Talent and Lifelong Education (BIT) in 2021 and Kyungsung University Research Grants in 2020.

References

  1. C. Haass and D. J. Selkoe, Soluble protein oligomers in neurode-generation: lessons from the Alzheimer's amyloid β-peptide, Nat. Rev. Mol. Cell Biol. 8 (2007), no. 2, 101-112.
  2. M. Yangling and H. Fred, Gage, adult hippocampal neurogenesis and its role in Alzheimer's disease, Mol. Neurodegener 6 (2011), no. 1, 85.
  3. Y. Lakshmisha Rao, B. Ganaraja, B. V. Murlimanju, T. Joy, A. Krishnamurthy, and A. Agrawal, Hippocampus and its involvement in Alzheimer's disease: a review, 3 Biotech 12 (2022), no. 2, DOI 10.1007/s13205-022-03123-4.
  4. R. De Man, G. J. Gang, X. Li, and G. Wang, Comparison of deep learning and human observer performance for detection and characterization of simulated lesions, J. Med. Imaging 6 (2019), no. 2, DOI 10.1117/1.JMI.6.2.025503.
  5. H. Hojjati, T. K. K. Ho, and N. Armanfard, Self-supervised anomaly detection: a survey and outlook, arXiv preprint, 2023, DOI 10.48550/arXiv.2205.05173.
  6. A. J. Larrazabal, N. Nieto, V. Peterson, D. H. Milone, and E. Ferrante, Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis, Proc. National Academy Sci. 117 (2020), no. 23, 12592-12594. https://doi.org/10.1073/pnas.1919012117
  7. A. S. Lundervold and A. Lundervold, An overview of deep learning in medical imaging focusing on MRI, Z. Med. Phys. 29 (2019), no. 2, 102-127. https://doi.org/10.1016/j.zemedi.2018.11.002
  8. F. Diaz-Pernas, M. Martinez-Zarzuela, M. Anton-Rodriguez, and D. Gonzalez-Ortega, A deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network, Healthcare 9 (2021), 153.
  9. O. Ronneberger, P. Fischer, and T. Brox, In Unet: convolutional networks for biomedical image segmentation, medical image computing and computer-assisted intervention - MICCAI 2015 (Cham), N. Navab, J. Hornegger, W. M. Wells, A. F. Frangi (eds.), Springer International Publishing, 2015, 234-241.
  10. F. Hardalac, F. Uysal, O. Peker, M. Ciceklidag, T. Tolunay, N. Tokgoz, U. Kutbay, B. Demirciler, and F. Mert, Fracture detection in wrist x-ray images using deep learning-based object detection models, Sensors (Basel) 22 (2021), no. 3, 1285.
  11. T. Schlegl, P. Seebock, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs, Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, information processing in medical imaging (Cham), Springer International Publishing, 2017, 146-157.
  12. C.-M. Kim, E. J. Hong, and R. C. Park, Chest x-ray outlier detection model using dimension reduction and edge detection, IEEE Access 9 (2021), 86096-86106.
  13. J. Wolleb, R. Sandkuhler, and P. C. Cattin, Descargan: diseasespecific anomaly detection with weak supervision, arXiv preprint, 2020, DOI 10.48550/arXiv.2007.14118.
  14. N. Pawlowski, M. J. Lee, M. Rajchl, S. G. McDonagh, E. Ferrante, K. Kamnitsas, S. Cooke, S. Stevenson, A. Khetani, T. Newman, F. A. Zeiler, R. Digby, J. P. Coles, D. Rueckert, D. K. Menon, V. F. J. Newcombe, and B. Glocker, Unsupervised lesion detection in brain ct using bayesian convolutional autoencoders, 2018.
  15. K. Armanious, C. Jiang, S. Abdulatif, T. Kustner, S. Gatidis, and B. Yang, Unsupervised medical image translation using cycleMeDGAN, (European Signal Processing Conference, A Coruna, Spain), 2019, DOI 10.23919/EUSIPCO.2019.8902799.
  16. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. WardeFarley, S. Ozair, A. Courville, and Y. Bengio, Generative adversarial nets, (Proceedings of the 27th International Conference on Neural information processing systems NIPS'14, Montreal, Canada), 2014, pp. 2672-2680.
  17. H. Zenati, C. S. Foo, B. Lecouat, G. Manek, and V. R. Chandrasekhar, Efficient GAN-based anomaly detection, arXiv preprint, 2018, DOI 10.48550/arXiv.1802.06222.
  18. J. Donahue, P. Krahenbuhl, and T. Darrell, Adversarial feature learning, (5th International Conference on Learning Representations, ICLR 2017), OpenReview. net, 2017.
  19. S. Akcay, A. A. Abarghouei, and T. P. Breckon, GANomaly: semi-supervised anomaly detection via adversarial training, Lecture Notes in Computer Science Vol. 11363, 2018, Springer, pp. 622-637.
  20. S. Akcay, A. A. Abarghouei, and T. Breckon, Skip-GANomaly: skip connected and adversarially trained encoder-decoder anomaly detection, (Int. Joint Conf. Neural Netw, Budapest, Hungary), 2019, pp. 1-8.
  21. M. A. F. Pimentel, D. A. Clifton, L. Clifton, and L. Tarassenko, A review of novelty detection, Signal Proc. 99 (2014), 215-249. https://doi.org/10.1016/j.sigpro.2013.12.026
  22. V. Chandola, A. Banerjee, and V. Kumar, Anomaly detection: a survey, ACM Comput. Surv. 41 (2009), no. 3, 1-58.
  23. E. Keogh and A. Mueen, Curse of dimensionality, Springer US, Boston, MA, 2017, 314-315.
  24. J. Zimmermann, A. Perry, M. Breakspear, M. Schirner, P. Sachdev, W. Wen, N. A. Kochan, M. Mapstone, P. Ritter, A. R. McIntosh, and A. Solodkin, Differentiation of Alzheimer's disease based on local and global parameters in personalized virtual brain models, NeuroImage: Clinical 19 (2018), 240-251. https://doi.org/10.1016/j.nicl.2018.04.017
  25. Yingjie Lin and Jianning Wu, A novel multichannel dilated convolution neural network for human activity recognition, Math. Probl. Eng. (2020), 5426532, DOI 10.1155/2020/5426532. 
  26. A. Lavin and S. Gray, Fast algorithms for convolutional neural networks, (IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA), 2016, pp. 4013-4021.
  27. S. Ioffe and C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift, Proc. 32nd Int. Conf. Machine Learn. 37 (2015), 448-456.
  28. M. Drozdzal, E. Vorontsov, G. Chartrand, S. Kadoury, and C. Pal, The importance of skip connections in biomedical image segmentation, (Deep Learning and Data Labeling for Medical Applications - First International Workshop, LABELS 2016, and Second International Workshop, DLMIA 2016, held in conjunction with MICCAI 2016, Athens, Greece), 2016, pp. 179-187.
  29. Y. Yang, R. Jin, and C. Xu, On the effects of skip connections in deep generative adversarial models, (Proc. 4th Int. Conf. on Computer Science and Artificaial Intelligence, Zhuhai, China), 2020, pp. 57-61.
  30. T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, Improved techniques for training GANs, (Proceedings of the 30th International Conference on Neural Information Processing Systems NIPS, Red Hook, NY, USA), 2016, pp. 2234-2242.
  31. M. Arjovsky, S. Chintala, and L. Bottou, Wasserstein generative adversarial networks, (Proceedings of the 34th International Conference on Machine Learning ICML), 2017, pp. 214-223.
  32. J. Cohen and P. Cohen, Applied multiple regression/correlation analysis for the behavioral sciences, L. Erlbaum Associates, Hillsdale, NJ, 1983.
  33. F. R. S. Karl Pearson, LIII. On lines and planes of closest fit to systems of points in space, London, Edinburgh, Dublin Phil. Mag. J. Sci. 2 (1901), no. 11, 559-572. https://doi.org/10.1080/14786440109462720
  34. W. Mustafa and M. Kader, A review of histogram equalization techniques in image enhancement application, J. Phys. Conf. Series. 1019 (2018), 012026.
  35. Claude Elwood Shannon, A mathematical theory of communication, the, Bell Syst. Tech. J. 27 (1948), 379-423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
  36. C. Thum, Measurement of the entropy of an image with application to image focusing, Optica Acta: Int. J. Opt. 31 (1984), no. 2, 203-211. https://doi.org/10.1080/713821475
  37. G. Huang, Z Liu, L. van der Maaten, and K. Q. Weinberger, Densely connected convolutional networks, (IEEE Conference on Computer Vision and Pattern Recognition CVPR), 2017, pp. 2261-2269.
  38. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, (IEEE Conference on Computer Vision and Pattern Recognition), 2016, pp. 770-778.
  39. C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi, Inception-v4, inception-ResNet and the impact of residual connections on learning, In Proceedings of the thirty-first AAAI conference on artificial intelligence, S. P. Singh, S. Markovitch (eds.), AAAI Press, 2017, 4278-4284.
  40. M. Tan and Q. V. Le, Efficientnet: rethinking model scaling for convolutional neural networks, In Proceedings of the 36th international conference on machine learning, ICML, K. Chaudhuri, R. Salakhutdinov (eds.) Proceedings of Machine Learning Research Vol. 97, PMLR, 2019, 6105-6114.
  41. L. van der Maaten and G. Hinton, Visualizing data using t-sne, J. Machine Learn. Res. 9 (2008), no. 86, 2579-2605.
  42. D. A. Lisin, M. A. Mattar, M. B. Blaschko, E. G. Learned-Miller, and M. C. Benfield, Combining local and global image features for object class recognition, (IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)-Workshops, San Diego, CA, USA), 2005, pp. 47-47.
  43. J. Pirnay and K. Chai, Inpainting transformer for anomaly detection, Image Analysis and Processing - ICIAP 2022-21st International Conference, Lecce, Italy, May 23-27, 2022, In Proceedings, part II, S. Sclaroff, C. Distante, M. Leo, G. M. Farinella, F. Tombari (eds.) Lecture Notes in Computer Science Vol. 13232, Springer, 2022, 394-406.
  44. K. Roth, L. Pemula, J. Zepeda, B. Scholkopf, T. Brox, and P. V. Gehler, Towards total recall in industrial anomaly detection, (IEEE/CVF conference on computer vision and pattern recognition, CVPR 2022, New Orleans, LA, USA), 2022, pp. 14298-14308.
  45. D.A. Gudovskiy, S. Ishizaka, and K. Kozuka, CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows, (IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, Waikoloa, HI, USA), 2022, pp. 1819-1828.
  46. C. Han, L. Rundo, K. Murao, T. Noguchi, Y. Shimahara, Z. A. ' Milacski, S. Koshino, E. Sala, H. Nakayama, and S. Satoh, Madgan: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction, BMC Bioinform. 22 (2021), no. 2, 31.